Search

Insufficient sample is a common problem in hyperspectral image (HSI) classification and an important factor causing to low accuracy. Adding weak supervision mechanism to model training is an effective way to solve this problem. In this article, we propose a weakly supervised HSI classification method with few samples based on intradomain sample expansion, which is anchored on the spatial correlation between samples. First, to reduce the negative effects of spectral mixing on pseudolabel generation and classifier training, we introduce the continuous side window filter to smooth the original HSIs band-by-band. Second, in order to better balance the correctness and representativeness of the generated pseudolabels, a novel method for sample selection and pseudolabel generation is proposed in this article. The method contains two branches, the segmentation graph based and the neighborhood relationship based. In the branch based on segmentation graphs, the polygon segmentation graph generated by the false color image is used to select the expansion samples. As a complementary branch, the branch based on neighborhood relationship exploits the neighborhood relationship and spectral similarity between samples to further select samples. Finally, in the classification stage, this article uses the broad learning system as a classifier to obtain the classification graph. Experiments on three publicly available datasets show that the method in this article can effectively achieve sample expansion and improve the classification accuracy and stability of HSIs in the case of insufficient labeled samples.

The demand for accurate indoor localization has become more and more urgent in location-based services (LBS). Since the traditional indoor localization is based on a single fingerprint, which is susceptible to environmental changes, it is hard to obtain high accuracy. In order to fill this gap, we propose a new multiple fingerprints method used in the indoor environment without extra measurement, and it can reduce the uncertainty caused by a single fingerprint. The multiple fingerprints are based on the signal Subspace and the received signal strength index (RSSI) and others, where the signal Subspace represents the characteristic representation of the received array signal and the RSSI represents the signal strength. First, we propose an algorithm named Subspace gradient boost decision tree (Subspace-GBDT) to obtain a strong classifier, which can make a successful prediction. Second, we propose another algorithm named double threshold assisted mode (DTAM) to combine multiple fingerprints. It can achieve accurate prediction by setting two different threshold parameters, the threshold of samples number and classifiers number, and reduce errors of matching. The experiment results show that the proposed method can obtain higher cumulative distribution function (CDF) value and localization accuracy than the traditional methods.

Prostate cancer is one of the most prevalent cancers among men. Early detection of this cancer could effectively increase the survival rate of the patient. In this paper, we propose a Bi-attention adversarial network for the prostate cancer segmentation automatically. The proposed architecture consists of the generator network and discriminator network. The generator network aims to generate the predicted mask of the input image, while the discriminator network aims to further improve the generator performance with adversarial learning by discriminating the generator predicted mask and the true label mask. For better improving the segmentation performance, we combine two attention mechanisms with the generator network to learn more global and local features. Extensive experiments on the T2-weighted (T2W) images have demonstrated our model could achieve state-of-the-art segmentation performance compared with other methods.

Essential tremor (ET) is a neurological disorder characterized by rhythmic, involuntary shaking of a part or parts of the body. The most common tremor is seen in the hands/arms and fingers. This paper presents an evaluation of ETs monitoring based on finger-to-nose test measurement as captured by small wireless devices working in shortwave or S-band frequency range. The acquired signals in terms of amplitude and phase information are used to detect a tremor in the hands. Linearly transforming raw phase data acquired in the S-band were carried out for calibrating the phase information and to improve accuracy. The data samples are used for classification using support vector machine algorithm. This model is used to differentiate the tremor and nontremor data efficiently based on secondary features that characterize ET. The accuracy of our measurements maintains linearity, and more than 90% accuracy rate is achieved between the feature set and data samples.

A non-intrusive sleep apnea detection system using a C-Band channel sensing technique is proposed to monitor sleep apnea syndrome in real time. The system utilizes perturbations of RF signals to differentiate between patient's breathing under normal and sleep apnea conditions. The peak distance calculation is used to obtain the respiratory rates. A comparison of the datasets generated by the proposed method and a wearable sensor is made using a concordance correlation coefficient to establish its accuracy. The results show that the proposed sensing technique exhibits high accuracy and robustness, with more than 80% concordance with the wearable breathing sensor. This method is, therefore, a good candidate for the real-time wireless detection of sleep apnea.